Background: Despite recent significant progress in the development of automatic sleep staging methods, building a good model still remains a big challenge for sleep studies with a small cohort due to ...the data-variability and data-inefficiency issues. This work presents a deep transfer learning approach to overcome these issues and enable transferring knowledge from a large dataset to a small cohort for automatic sleep staging. Methods: We start from a generic end-to-end deep learning framework for sequence-to-sequence sleep staging and derive two networks as the means for transfer learning. The networks are first trained in the source domain (i.e. the large database). The pretrained networks are then finetuned in the target domain (i.e. the small cohort) to complete knowledge transfer. We employ the Montreal Archive of Sleep Studies (MASS) database consisting of 200 subjects as the source domain and study deep transfer learning on three different target domains: the Sleep Cassette subset and the Sleep Telemetry subset of the Sleep-EDF Expanded database, and the Surrey-cEEGrid database. The target domains are purposely adopted to cover different degrees of data mismatch to the source domains. Results: Our experimental results show significant performance improvement on automatic sleep staging on the target domains achieved with the proposed deep transfer learning approach. Conclusions: These results suggest the efficacy of the proposed approach in addressing the above-mentioned data-variability and data-inefficiency issues. Significance: As a consequence, it would enable one to improve the quality of automatic sleep staging models when the amount of data is relatively small.<xref ref-type="fn" rid="fn1"> 1 1
The source code and the pretrained models are published at https://github.com/pquochuy/sleep_transfer_learning .
Moving microphones allow for the fast acquisition of sound-field data that encode acoustic impulse responses in time-invariant environments. Corresponding decoding algorithms use the knowledge of ...instantaneous microphone positions for relating the dynamic samples to a positional context and solving the involved spatio-temporal channel estimation problem subject to the particular parameterization model. Usually, the resulting parameter estimates are supposed to remain widely unaffected by the Doppler effect despite the continuously moving sensor. However, this assumption raises issues from the physical point of view. So far, mathematical investigations into the actual meaning of the Doppler effect for such dynamic sampling procedures have been barely provided. Therefore, in this paper, we propose a new generic concept for the dynamic sampling model, introducing a channel representation that is explicitly based on the instantaneous Doppler shift according to the microphone trajectory. Within this model, it can be clearly seen that exact trajectory tracking implies exact Doppler-shift rendering and, thus, enables unbiased parameter recovery. Further, we investigate the impact of non-perfect trajectory data and the resulting Doppler-shift mismatches. Also, we derive a general analysis scheme that decomposes the microphone signal along with the encoded parameters into particular subbands of Doppler-shifted frequency components. Finally, for periodic excitation, we exactly characterize the Doppler-shift influences in the sampled signal by convolution operations in the frequency domain with trajectory-dependent filters.
•Multimethod rs-fMRI analysis reveals common hubs.•Experiment identifies areas relevant for ingestive behavior.•Experiment identifies interaction of metabolic state and glucose administration.
A ...major regulatory task of the organism is to keep brain functions relatively constant in spite of metabolic changes (e.g., hunger vs. satiety) or availability of energy (e.g., glucose administration). Resting-state functional magnetic resonance imaging (rs-fMRI) can reveal resulting changes in brain function but previous studies have focused mostly on the hypothalamus. Therefore, we took a whole-brain approach and examined 24 healthy normal-weight men once after 36 h of fasting and once in a satiated state (six meals over the course of 36 h). At the end of each treatment, rs-fMRI was recorded before and after the oral administration of 75 g of glucose. We calculated local connectivity (regional homogeneity ReHo), global connectivity (degree of centrality DC), and amplitude (fractional amplitude of low-frequency fluctuation fALFF) maps from the rs-fMRI data. We found that glucose administration reduced all measures selectively in the left supplementary motor area and increased ReHo and fALFF in the right middle and superior frontal gyri. For fALFF, we observed a significant interaction between metabolic states and glucose in the left thalamus. This interaction was driven by a fALFF increase after glucose treatment in the hunger relative to the satiety condition. Our results indicate that fALFF analysis is the most sensitive measure to detect effects of metabolic states on resting-state brain activity. Moreover, we show that multimethod rs-fMRI provides an unbiased approach to identify spontaneous brain activity associated with changes in homeostasis and caloric intake.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
Resting-state functional magnetic resonance imaging (rs-fMRI) has become an essential measure to investigate the human brain's spontaneous activity and intrinsic functional connectivity. Several ...studies including our own previous work have shown that the brain controls the regulation of energy expenditure and food intake behavior. Accordingly, we expected different metabolic states to influence connectivity and activity patterns in neuronal networks.
The influence of hunger and satiety on rs-fMRI was investigated using three connectivity models (local connectivity, global connectivity and amplitude rs-fMRI signals). After extracting the connectivity parameters of 90 brain regions for each model, we used sequential forward floating selection strategy in conjunction with a linear support vector machine classifier and permutation tests to reveal which connectivity model differentiates best between metabolic states (hunger vs. satiety).
We found that the amplitude of rs-fMRI signals is slightly more precise than local and global connectivity models in order to detect resting brain changes during hunger and satiety with a classification accuracy of 81%.
The amplitude of rs-fMRI signals serves as a suitable basis for machine learning based classification of brain activity. This opens up the possibility to apply this combination of algorithms to similar research questions, such as the characterization of brain states (e.g., sleep stages) or disease conditions (e.g., Alzheimer's disease, minimal cognitive impairment).
The hypothalamus and insular cortex play an essential role in the integration of endocrine and homeostatic signals and their impact on food intake. Resting-state functional connectivity alterations ...of the hypothalamus, posterior insula (PINS) and anterior insula (AINS) are modulated by metabolic states and caloric intake. Nevertheless, a deeper understanding of how these factors affect the strength of connectivity between hypothalamus, PINS and AINS is missing. This study investigated whether effective (directed) connectivity within this network varies as a function of prandial states (hunger vs. satiety) and energy availability (glucose levels and/or hormonal modulation). To address this question, we measured twenty healthy male participants of normal weight twice: once after 36 h of fasting (except water consumption) and once under satiated conditions. During each session, resting-state functional MRI (rs-fMRI) and hormone concentrations were recorded before and after glucose administration. Spectral dynamic causal modeling (spDCM) was used to assess the effective connectivity between the hypothalamus and anterior and posterior insula. Using Bayesian model selection, we observed that the same model was identified as the most likely model for each rs-fMRI recording. Compared to satiety, the hunger condition enhanced the strength of the forward connections from PINS to AINS and reduced the strength of backward connections from AINS to PINS. Furthermore, the strength of connectivity from PINS to AINS was positively related to plasma cortisol levels in the hunger condition, mainly before glucose administration. However, there was no direct relationship between glucose treatment and effective connectivity. Our findings suggest that prandial states modulate connectivity between PINS and AINS and relate to theories of interoception and homeostatic regulation that invoke hierarchical relations between posterior and anterior insula.
•We use spectral DCM and BMS to test whether prandial states and glucose administration altered EC at rest between hypothalamus and insula.•Hunger (relative to satiety) strengthened forward connections from posterior to anterior insula and reduced backward connections between these same areas.•In the hunger before glucose administration, connection strength from right posterior to anterior insula was positively associated with cortisol levels.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
► A feature-extraction method based on invariant integration is presented. ► Experiments show a superior performance compared to standard features. ► The new features benefit from the combination ...with speaker-adaptation methods.
This work presents a feature-extraction method that is based on the theory of invariant integration. The invariant-integration features are derived from an extended time period, and their computation has a very low complexity. Recognition experiments show a superior performance of the presented feature type compared to cepstral coefficients using a mel filterbank (MFCCs) or a gammatone filterbank (GTCCs) in matching as well as in mismatching training-testing conditions. Even without any speaker adaptation, the presented features yield accuracies that are larger than for MFCCs combined with vocal tract length normalization (VTLN) in matching training-test conditions. Also, it is shown that the invariant-integration features (IIFs) can be successfully combined with additional speaker-adaptation methods to further increase the accuracy. In addition to standard MFCCs also contextual MFCCs are introduced. Their performance lies between the one of MFCCs and IIFs.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
One objective way to evaluate the effect of noise reduction algorithms in hearing aids is to measure the increase in signal-to-noise-ratio (SNR). To this end, Hagerman and Olofsson presented a method ...where multiple recordings take place and the phase of one signal is inverted between the measurements. This phase inversion method allows one to separate signal and noise at the output of the hearing aid so that the increase in SNR can be evaluated. However, only two signals can be distinguished, for example, speech and noise. As many realistic situations include more than two signals, we extend the method to an arbitrary number of signals. Two different approaches are discussed. For the first one, groups of the signals are created and presented in such a way that the basic phase inversion method can be used. The second, more efficient approach defines a linear system of equations considering all signals. As the robustness of this approach depends on the structure of the system matrix, the design of this matrix is described in detail. To prove the concept, the proposed efficient method was applied to a setup in which nine different signals were presented by eight loudspeakers, and an analysis of errors was performed. With this setup, a state-of-the-art hearing aid was analyzed for four different settings, that is, with the digital noise reduction or the directional microphones turned on or off. As a result, the SNRs for all directions can be investigated individually.
To study the interplay of metabolic state (hungry vs. satiated) and glucose administration (including hormonal modulation) on brain function, resting-state functional magnetic resonance imaging ...(rs-fMRI) and blood samples were obtained in 24 healthy normal-weight men in a repeated measurement design. Participants were measured twice: once after a 36 h fast (except water) and once under satiation (three meals/day for 36 h). During each session, rs-fMRI and hormone concentrations were recorded before and after a 75 g oral dose of glucose. We calculated the amplitude map from blood-oxygen-level-dependent (BOLD) signals by using the fractional amplitude of low-frequency fluctuation (fALFF) approach for each volunteer per condition. Using multiple linear regression analysis (MLRA) the interdependence of brain activity, plasma insulin and blood glucose was investigated. We observed a modulatory impact of fasting state on intrinsic brain activity in the posterior cingulate cortex (PCC). Strikingly, differences in plasma insulin levels between hunger and satiety states after glucose administration at the time of the scan were negatively related to brain activity in the posterior insula and superior frontal gyrus (SFG), while plasma glucose levels were positively associated with activity changes in the fusiform gyrus. Furthermore, we could show that changes in plasma insulin enhanced the connectivity between the posterior insula and SFG. Our results indicate that hormonal signals like insulin alleviate an acute hemostatic energy deficit by modifying the homeostatic and frontal circuitry of the human brain.
The perceived quality of a sound played in a closed room is often degraded by the added reverberation. In order to combat these effects, the methods of room impulse response equalization may be used. ...Typically, properties of the human auditory system, such as temporal masking, are used for a better control of the late echoes. There, a prefilter is used to modify the played signal, which renders the echoes inaudible for a given position. When targeting a human listener who is always performing small movement, the method fails due to the spatial mismatch. In such a case, a whole volume needs to be equalized, which requires a huge amount of measurements. In this work, we propose to reduce this burden by measuring only a random subset of the required room impulse responses and reconstruct a grid employing sparse methods. By further interpolation an equalization of the whole target area is achieved.